Upload Date | December 28 2024 02:08 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 732G |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi Redmi Note 10 Pro |
Model ID | Xiaomi M2101K6G |
Motherboard | sweet |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.30 GHz |
Memory Information | |
---|---|
Size | 5.44 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
228
42.4 IPS |
|
Image Classification (HP)
|
100% |
229
42.6 IPS |
|
Image Classification (Q)
|
100% |
700
130.2 IPS |
|
Image Segmentation (SP)
|
100% |
280
4.54 IPS |
|
Image Segmentation (HP)
|
100% |
281
4.56 IPS |
|
Image Segmentation (Q)
|
98% |
760
12.4 IPS |
|
Pose Estimation (SP)
|
100% |
1062
1.24 IPS |
|
Pose Estimation (HP)
|
100% |
1015
1.18 IPS |
|
Pose Estimation (Q)
|
84% |
1636
1.94 IPS |
|
Object Detection (SP)
|
100% |
207
16.4 IPS |
|
Object Detection (HP)
|
100% |
210
16.7 IPS |
|
Object Detection (Q)
|
83% |
697
56.3 IPS |
|
Face Detection (SP)
|
100% |
668
7.94 IPS |
|
Face Detection (HP)
|
100% |
670
7.96 IPS |
|
Face Detection (Q)
|
95% |
1574
18.8 IPS |
|
Depth Estimation (SP)
|
100% |
886
6.83 IPS |
|
Depth Estimation (HP)
|
99% |
863
6.65 IPS |
|
Depth Estimation (Q)
|
64% |
1555
14.2 IPS |
|
Style Transfer (SP)
|
89% |
1684
2.19 IPS |
|
Style Transfer (HP)
|
89% |
1735
2.25 IPS |
|
Style Transfer (Q)
|
98% |
3765
4.85 IPS |
|
Image Super-Resolution (SP)
|
100% |
476
17.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
473
17.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
929
34.4 IPS |
|
Text Classification (SP)
|
100% |
275
367.0 IPS |
|
Text Classification (HP)
|
100% |
275
367.5 IPS |
|
Text Classification (Q)
|
88% |
552
744.9 IPS |
|
Machine Translation (SP)
|
100% |
425
7.32 IPS |
|
Machine Translation (HP)
|
100% |
440
7.58 IPS |
|
Machine Translation (Q)
|
50% |
354
12.6 IPS |